Why did we open-source our inference engine? Read the post

← Catalog

BAAI/bge-reranker-large

Open comparison →

Primitive: /score · Score · XLM-RoBERTa

We have updated the new reranker, supporting larger lengths, more languages, and achieving better performance.

Multilingual

Overview

Hardware: — drives latency, throughput & cost

Size560M params
Tasks /score
Licensemit
Languagesen, zh
Latency52 ms
Throughput21.1K tok/s
Cost$0.011 /1M tok

Cost is approximate — computed from list GPU prices; your actual price depends on the provider you deploy SIE with.

Scoring

Inputstext
Max sequence length512

Benchmarks

AskUbuntuDupQuestions

technology reranking en

Duplicate question detection from AskUbuntu

Corpus: 6,743 Queries: 360
Quality
ndcg at 10 0.6404
map at 10 0.4835
mrr at 10 0.7114
Performance L4 b1 c16
Query 6.6K tok/s
Query p50 41.4ms
Reference →

CMedQAv1Reranking

medical reranking zh

Chinese medical question answering reranking (v1)

Corpus: 100,000 Queries: 2,000
Quality
map at 10 0.8164
mrr at 10 0.8492
Reference →

CMedQAv2Reranking

medical reranking zh

Chinese medical question answering reranking (v2)

Corpus: 108,000 Queries: 4,000
Quality
map at 10 0.8361
mrr at 10 0.8697
Reference →

MMarcoReranking

general reranking zh

Multilingual MARCO passage reranking (Chinese)

Quality
map at 10 0.3638
mrr at 10 0.3668
Performance L4 b1 c16
Reference →

T2Reranking

general reranking zh

Chinese passage ranking benchmark

Quality
map at 10 0.5623
mrr at 10 0.7770
Reference →

Open source inference for agents

Open-source inference for the models behind your agents. Run it yourself, or let us run it for you.

Github 2.1K

Contact us

Tell us about your use case and we'll get back to you shortly.

Apply for an inference grant

Free capacity on our hosted cluster for selected projects. Tell us what you run and we reply by email.